diffusers
https://github.com/huggingface/diffusers
Python
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported3 Subscribers
Add a CodeTriage badge to diffusers
Help out
- Issues
- No LoRA fine-tuning example for RFD4-Proteina
- [training scripts] `--logit_mean` biases timesteps in the opposite direction to the SD3 paper (positive m oversamples low noise)
- UniPC and DPM-Solver with use_flow_sigmas condition the model on integer timesteps while integrating with float sigmas
- Flux and LTX pipelines do not forward the generator to stochastic scheduler steps
- [chore] remove smoke test file.
- DreamLite: disabling attention slicing replaces the GQA processor and breaks inference
- Add reverse conversion script (Diffusers → original CogVideoX)
- Add an RFD4-Proteina LoRA training example
- Kandinsky 6: add context-parallel (_cp_plan) support to Kandinsky6Transformer3DModel
- fix(schedulers): skip noise at terminal DDPM step when no predecessor exists
- Docs
- Python not yet supported